You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
Intuitively, differentiable layered representation learning (deep learning) is in some ways closer to classical signal processing than it is to other branches of AI and ML, due to its substrate (stack of learned linear filters with a hardcoded differentiable non-linearity)
I wonder how differently the field would have evolved if we had chosen to use terminology derived from the world of signal processing instead of neuropsychology
Signal Processing influenced (and still) the pattern recognition based AI more, the formal conservatism of both signal processing community and AI blurred that vision until the success of CNN was demonstrated.
http://www.lighton.io it already exists.
I tend to fall back to a similar explanation when I’m talking deep learning to people in my group (mostly Elec. Engineers).
Filters filters everywhere
I wish we never used the neuropsychology terminology. It's inaccurate and had caused hype and misinformation and attracted pseudo tech bloggers who know little about ML
Where’s the learning, feedback? Filters are filters.
The funny thing is that the brain is a discrete signal (spike) processor, a highly precise one (millisecond precision). Those who gave us artificial neural networks were obviously unaware of this.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
